- You are here:
- GT Home
Patient Similarity Learning through Distance Metric Learning and Interactive Visualization
The objective of patient similarity is to quantitatively measure how similar patients are to each other. The challenges of comprehensive patient similarity are the following:
* How to leverage physician feedback into the similarity computation?
* How to integrate multiple sources of clinical information or patient similarity computation?
* How to compare patients at different stages of disease progression?
* How to incrementally update the existing patient similarity functions as new data arrive?
* How to present the similarity in an intuitive way?
In this work, we will present the comprehensive patient similarity
framework that answers those questions. The core of the framework is the combination of advanced distance metric learning algorithms and novel visualization techniques. We also present some empirical studies on real patient data from a large healthcare network over 200K patients.
Finally, we envision the patient similarity framework can enable many important clinical applications such as comparative effectiveness research (CER), treatment recommendation, and physician comparison model.
Dr. Jimeng Sun is a research staff member at IBM TJ Watson Research Center. Dr. Sun graduated with PhD in Compuser Science in Carnegie Mellon University in the fall 2007. His advisor was Prof. Christos Faloutsos. He studied in Computer science department at Carnegie Mellon University from 2003 to 2007. His research focus is on healthcare analytics and informatics, large-scale data mining, graph mining, high-dimensional data mining such as time series, matrices, and tensors (data cubes) and visual analytics. Dr. Sun has received ICDM best research paper in 2007 and KDD Dissertation runner-up award in 2008 and SDM best research paper in 2007.